论文信息 - A-Learning for approximate planning

A-Learning for approximate planning

Abstract We consider a new algorithm for reinforcement learning called A-learning. A-learning learns the advantages from a single training set. We compare A-learning with function approximation to Q-learning with function approximation and find that because A-learning approximates only the advantages it is less likely to exhibit bias due to the function approximation as compared to Q-learning.We consider a new algorithm for reinforcement learning called A-learning. A-learning learns the advantages from a single training set. We compare A-learning with function approximation to Q-learning with function approximation and find that because A-learning approximates only the advantages it is less likely to exhibit bias due to the function approximation as compared to Q-learning.

[1] Alfred O. Hero,et al. Multi-target Sensor Management Using Alpha-Divergence Measures , 2003, IPSN.

[2] Leo Breiman,et al. Random Forests , 2001, Machine Learning.

[3] Yishay Mansour,et al. Approximate Planning in Large POMDPs via Reusable Trajectories , 1999, NIPS.

[4] R. Tibshirani. Regression Shrinkage and Selection via the Lasso , 1996 .

[5] Richard S. Sutton,et al. Reinforcement Learning: An Introduction , 1998, IEEE Trans. Neural Networks.

[6] C. F. Jeff Wu,et al. Experiments: Planning, Analysis, and Parameter Design Optimization , 2000 .

[7] S. Murphy,et al. Optimal dynamic treatment regimes , 2003 .

[8] Leo Breiman,et al. Bagging Predictors , 1996, Machine Learning.

[9] D. Kupfer,et al. Background and rationale for the sequenced treatment alternatives to relieve depression (STAR*D) study. , 2003, The Psychiatric clinics of North America.

[10] J. Lieberman,et al. The National Institute of Mental Health Clinical Antipsychotic Trials of Intervention Effectiveness (CATIE) project: schizophrenia trial design and protocol development. , 2003, Schizophrenia bulletin.

[11] K. Davis,et al. National Institute of Mental Health Clinical Antipsychotic Trials of Intervention Effectiveness (CATIE): Alzheimer disease trial methodology. , 2001, The American journal of geriatric psychiatry : official journal of the American Association for Geriatric Psychiatry.